claude-code-usage

Files (1)

• SKILL.md

SKILL.md (first lines)

# Claude Code Best Practices

## Language Rule

- **Always respond in the same language the user is using.** If the user asks in Chinese, respond in Chinese. If in English, respond in English.

## Context Management Rules

| Rule | Why |
|------|-----|
| One window = one task | Mixing tasks pollutes context and degrades output quality |
| Use `/clear` over `/compact` | Clean start is more reliable than compressed context |
| `/clear` after complex tasks | Prevents old context from interfering with new work |
| Copy key info to new windows | Don't rely on context persistence — paste critical details |

## Task Execution Strategy

| Task Type | Recommended Approach |
|-----------|---------------------|
| Small bug fix (few lines) | Describe directly, let Claude modify in-place |
| Large feature / refactor | `/plan` → review approach → `/clear` → paste plan → execute step by step |
| Multi-file changes | Must use `/plan` workflow — never modify multiple files without a plan |
| Code analysis / learning | Ask Claude to analyze directly — no plan needed |
| Debugging | Provide error message + file path + relevant code — ask for root cause |

## Prompt Techniques

### Do This

- Give specific paths: *"Modify the `_transfer` function in `src/MyToken.sol`"*
- Give examples: *"Input: 100 tokens, Expected: 95 tokens after 5% fee"*
- Set boundaries: *"Only modify this function, don't touch other code"*
- Reference tests: *"The fix should make `test_transfer_feeDeduction` pass"*

### Avoid This

- Vague references: *"Modify that transfer function"* — which one? Where?
- Open-ended requests without constraints: *"Make it better"*
- Multiple unrelated tasks in one message

## Ambiguity Resolution — When Instructions Are Unclear

When a user instruction is vague, open-ended, or could be interpreted in multiple ways, do NOT guess and proceed. Proactively analyze the instruction and present all possible interpretations for the user to confirm before taking action.

### Trigger Conditions

Activate ambiguity resolution when the instruction matches ANY of these patterns:

| Pattern | Example |
|---------|---------|
| No target specified | "优化一下" — optimize what? |
| Multiple possible scopes | "加个检查" — which function? what kind of check? |
| Unclear boundary | "改一下权限" — add? remove? which role? |
| Implicit context | "跟上次一样处理" — what was "last time"? |
| Conflicting possibilities | "处理一下安全问题" — which vulnerability? what level? |

### Analysis Dimensions

When ambiguity is detected, analyze across these dimensions:

1. **Scope** — Which files / contracts / functions could be affected?
2. **Action** — What operation is intended? (add / modify / delete / refactor / fix)
3. **Skill match** — Which skills are relevant? Map each interpretation to applicable /skill
4. **Impact** — What side effects could each interpretation have?
5. **Constraints** — Are there implicit boundaries the user might assume?

### Output Format

Present findings as a numbered list:

```
我检测到你的指令存在多种可能的解读，在开始之前需要确认边界：

**可能的解读：**

1. **[解读A]** — [具体描述]
   - 涉及：[files / contracts]
   - 关联 skill：/skill-name
   - 影响范围：[scope]

2. **[解读B]** — [具体描述]
   - 涉及：[files / contracts]
   - 关联 skill：/skill-name
   - 影响范围：[scope]

**请确认：**
- 你想要哪个解读？（可多选）
- 是否有额外的约束条件？
```

### Example

```
User: "处理一下这个合约的安全问题"

AI: 我检测到你的指令存在多种可能的解读：

1. **运行 Slither 静态分析** — 用 slither MCP 扫描，修复高危问题
   - 关联 skill：/solidity-security
   - 影响范围：仅修复工具检测到的问题

2. **手动安全审计** — 按审计清单逐项检查（重入、权限、输入验证等）
   - 关联 skill：/solidity-audit
   - 影响范围：完整审查，可能涉及较多修改

3. **修复已知漏洞** — 你已知有特定安全问题，需要定位并修复
   - 关联 skill：/solidity-security
   - 影响范围：仅限特定问题

4. **DeFi 安全加固** — 添加防鲸鱼、防闪电贷等保护机制
   - 关联 skill：/defi-security
   - 影响范围：可能改变合约接口

请确认你想要哪个方向？
```

### Key Rules

| Rule | Why |

From ComeOnOliver/skillshub, MIT.

More from ComeOnOliver/skillshub